AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial Domains

Yidan Sun, Mengying Zhu, Feiyue Chen, Yangyang Wu, Xiaolei Dan, Mengyuan Yang, Xiaolin Zheng, Shenglin Ben

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Fine-tuning generalization and delta compression · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SFT stage before contrastive learning (ablation)TermGPT-Qwen3 · JecQA QCAaccuracy: 0.796 -> 0.858Improved
add SFT stage before contrastive learning (ablation)TermGPT-Qwen3 · Financial Regulations QCAaccuracy: 0.818 -> 0.908Improved
add contrastive learning on top of SFT (ablation)TermGPT-Qwen3 · JecQA QCAaccuracy: 0.834 -> 0.858Improved
add contrastive learning on top of SFT (ablation)TermGPT-Qwen3 · Financial Regulations QCAaccuracy: 0.864 -> 0.908Improved
add token-level contrastive learning (ablation)TermGPT-Qwen3 · JecQA QCAaccuracy: 0.844 -> 0.858Improved
add token-level contrastive learning (ablation)TermGPT-Qwen3 · Financial Regulations QCAaccuracy: 0.899 -> 0.908Improved
add sentence-level contrastive learning (ablation)TermGPT-Qwen3 · JecQA QCAaccuracy: 0.849 -> 0.858Improved
add sentence-level contrastive learning (ablation)TermGPT-Qwen3 · Financial Regulations QCAaccuracy: 0.894 -> 0.908Improved
use Qwen3-8B instead of LLaMA-8B backbone (ablation)TermGPT · JecQA QCAaccuracy: 0.681 -> 0.858Improved
use Qwen3-8B instead of LLaMA-8B backbone (ablation)TermGPT · Financial Regulations QCAaccuracy: 0.856 -> 0.908Improved
TermGPT multi-level CL vs best 8B contrastive baselineQwen3-8B · JecQA QCAaccuracy: 0.834 -> 0.858Improved
TermGPT vs commercial LLMsTermGPT-Qwen3 · JecQA QCAaccuracy: 0.894 -> 0.858Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy